T. Cover
Selected Papers on Neural Nets, Learning and Pattern Recognition

1. Thomas M. Cover. Geometrical and Statistical Properties of Linear Threshold Devices (Ph.D. thesis). Stanford Electronics Laboratories Technical Report #6107-1 , May 1964.

2. Thomas M. Cover. Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition. IEEE Transactions on Electronic Computers, EC-14(3):326--334, June 1965. Reprinted in Artificial Neural Networks: Concepts and Theory, IEEE Computer Society Press, Los Alamitos, Calif., 1992, eds. P. Mehra and B. Wah.

   Papers 1 & 2: Capacity of neurons and a bound on the capacity of feed forward neural nets. Generalization begins where learning ends.
   
   

3. T.M. Cover and P.E. Hart. Nearest Neighbor Pattern Classification. IEEE Transactions on Information Theory, IT-13(1):21--27, January 1967. Reprinted in Pattern Recognition, Chinese University Press, Hong Kong, 1980. ed. by K.S. Fu.

   Factor of two bound on risk.
   
   

4. Thomas M. Cover. Estimation by the Nearest Neighbor Rule. IEEE Transactions on Information Theory, IT-14(1):50--55, January 1968.

   Factor of two bound on the ratio of NN risk to Bayes risk.
   
   

5. Martin E. Hellman and Thomas M. Cover. Learning with Finite Memory. Ann. Math. Stat., 41(3):765--782, June 1970. Russian translation: ``Obucheniye c Konechnoy Pamyatyu,'' Matematika, 17(3):137-156, 1973.

   See also On Memory Saved by Randomization.
   
   

6. Thomas M. Cover. Generalization on Patterns Using Kolmogorov Complexity. Proceedings of the First International Joint Conference on Pattern Recognition, Washington, D.C., October 1973.
   
   

7. Andrew R. Barron and Thomas M. Cover. Minimum Complexity Density Estimation. IEEE Transactions on Information Theory, 37(4): 1034-1054, July 1991.

   Applies idea of the Kolmogorov sufficient statistic to density estimation. Defines index of resolvability.
   
   

   ---